Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    semicolons and parentheses, which are commonly used in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }?>
    -0.49
    .*")]
    -0.47
     clips
    -0.44
    }}}}
    -0.42
     meets
    -0.41
    </tfoot>
    -0.41
     Voor
    -0.41
     menus
    -0.41
    berdayakan
    -0.41
    setPreferred
    -0.41
    POSITIVE LOGITS
    帖最后由
    0.88
    SequentialGroup
    0.69
     kasarigan
    0.64
    httphttps
    0.61
     gynhyrchwyd
    0.48
    ----</
    0.45
    richTextPanel
    0.43
    tonode
    0.43
     CWE
    0.42
    astify
    0.42
    Act Density 0.051%

    No Known Activations